paper-with-me

홈 › Papers

Modeling Expert AI Diagnostic Alignment via Immutable Inference Snapshots

2026-02-26 · Dimitrios P. Panagoulias, Evangelia-Aikaterini Tsichrintzi, Georgios Savvidis, Evridiki Tsoureli-Nikita arxiv

Human-in-the-loop validation is essential in safety-critical clinical AI, yet the transition between initial model inference and expert correction is rarely analyzed as a structured signal. We introduce a diagnostic alignment framework in which the AI-generated image based report is preserved as an immutable inference state and systematically compared with the physician-validated outcome. The inference pipeline integrates a vision-enabled large language model, BERT- based medical entity extraction, and a Sequential Language Model Inference (SLMI) step to enforce domain-consistent refinement prior to expert review. Evaluation on 21 dermatological cases (21 complete AI physician pairs) em- ployed a four-level concordance framework comprising exact primary match rate (PMR), semantic similarity-adjusted rate (AMR), cross-category alignment, and Comprehensive Concordance Rate (CCR). Exact agreement reached 71.4% and remained unchanged under semantic similarity (t = 0.60), while structured cross-category and differential overlap analysis yielded 100% comprehensive concordance (95% CI: [83.9%, 100%]). No cases demonstrated complete diagnostic divergence. These findings show that binary lexical evaluation substantially un- derestimates clinically meaningful alignment. Modeling expert validation as a structured transformation enables signal-aware quantification of correction dynamics and supports traceable, human aligned evaluation of image based clinical decision support systems.

📄 PDF Abstract BibTeX arXiv:2602.22973

Code (0)

등록된 구현이 없습니다.

Tasks

Semantic Similarity

Similar Papers 제목 키워드 기반

MedMoE: Modality-Specialized Mixture of Experts for Medical Vision-Language Understanding

2025-06-10 · Shivang Chopra, Lingchao Mao, Gabriela Sanchez-Rodriguez, Andrew J Feola 외

Different medical imaging modalities capture diagnostic information at varying spatial resolutions, from coarse global patterns to fine-grained localized structures. However, most existing vision-language frameworks in t…

DiagnosticMixture-of-Experts

A Client-server Deep Federated Learning for Cross-domain Surgical Image Segmentation

2023-06-14 · Ronast Subedi, Rebati Raman Gaire, Sharib Ali, Anh Nguyen 외

This paper presents a solution to the cross-domain adaptation problem for 2D surgical image segmentation, explicitly considering the privacy protection of distributed datasets belonging to different centers. Deep learnin…

DiagnosticDomain AdaptationFederated LearningImage Segmentation+3

MApLe: Multi-instance Alignment of Diagnostic Reports and Large Medical Images

2026-04-15 · Felicia Bader, Philipp Seeböck, Anastasia Bartashova, Ulrike Attenberger 외 arxiv

In diagnostic reports, experts encode complex imaging data into clinically actionable information. They describe subtle pathological findings that are meaningful in their anatomical context. Reports follow relatively con…

MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution

2026-04-29 · Chunzheng Zhu, Jiaqi Zeng, Junyu Jiang, Jianxin Lin 외 arxiv

High-precision medical diagnosis relies not only on static imaging features but also on the implicit diagnostic memory experts instantly invoke during image interpretation. We pinpoint a fundamental cognitive misalignmen…

Reinforcement LearningMedical Diagnosis

LEAD: Layer-wise Expert-aligned Decoding for Faithful Radiology Report Generation

2026-02-04 · Ruixiao Yang, Yuanhe Tian, Xu Yang, Huiqi Li 외 arxiv

Radiology Report Generation (RRG) aims to produce accurate and coherent diagnostics from medical images. Although large vision language models (LVLM) improve report fluency and accuracy, they exhibit hallucinations, gene…